dc.contributor.author | Lin, Dahua | |
dc.contributor.author | Grimson, Eric | |
dc.contributor.author | Fisher, John W., III | |
dc.date.accessioned | 2012-10-15T13:26:47Z | |
dc.date.available | 2012-10-15T13:26:47Z | |
dc.date.issued | 2010-12 | |
dc.identifier.uri | http://hdl.handle.net/1721.1/73948 | |
dc.description.abstract | We present a method for constructing dependent Dirichlet processes. The new approach
exploits the intrinsic relationship between Dirichlet and Poisson processes
in order to create a Markov chain of Dirichlet processes suitable for use as a prior
over evolving mixture models. The method allows for the creation, removal, and
location variation of component models over time while maintaining the property
that the random measures are marginally DP distributed. Additionally, we derive
a Gibbs sampling algorithm for model inference and test it on both synthetic and
real data. Empirical results demonstrate that the approach is effective in estimating
dynamically varying mixture models. | en_US |
dc.language.iso | en_US | |
dc.publisher | Neural Information Processing Systems Foundation (NIPS) | en_US |
dc.relation.isversionof | http://nips.cc/Conferences/2010/Program/accepted-papers.php | en_US |
dc.rights | Creative Commons Attribution-Noncommercial-Share Alike 3.0 | en_US |
dc.rights.uri | http://creativecommons.org/licenses/by-nc-sa/3.0/ | en_US |
dc.source | MIT web domain | en_US |
dc.title | Construction of Dependent Dirichlet Processes Based on Poisson Processes | en_US |
dc.type | Article | en_US |
dc.identifier.citation | D. Lin et al. "Construction of Dependent Dirichlet Processes based on Poisson Processes" Neural Information Processing Systems 2010. | en_US |
dc.contributor.department | Massachusetts Institute of Technology. Computer Science and Artificial Intelligence Laboratory | en_US |
dc.contributor.mitauthor | Lin, Dahua | |
dc.contributor.mitauthor | Grimson, Eric | |
dc.contributor.mitauthor | Fisher, John W., III | |
dc.relation.journal | Neural Information Processing Systems | en_US |
dc.eprint.version | Author's final manuscript | en_US |
dc.type.uri | http://purl.org/eprint/type/ConferencePaper | en_US |
dc.identifier.orcid | https://orcid.org/0000-0003-4844-3495 | |
dc.identifier.orcid | https://orcid.org/0000-0002-6192-2207 | |
mit.license | OPEN_ACCESS_POLICY | en_US |
mit.metadata.status | Complete | |